LALDM: A Multimodal Aspect-Level Text Analysis Method and Its Application in Online Consumer Electronics
Bibliographic record
Abstract
Aspect term extraction and aspect level sentiment analysis are key tasks. Although in the multimodal field, performance is enhanced by placing these two tasks in a unified framework, there is still room for improvement in aspect level analysis for short texts. Firstly, existing research has shown that texts usually play a more important role in online reviews than images. Therefore, we use a large language model to automatically label the text, thereby enhancing its contribution of text to aspect level analysis. Secondly, we use a better depth model than most existing studies, DenseNet, to enhance the effectiveness of image analysis. We integrated text analysis and image analysis modules to form a unified framework for aspect term extraction and aspect sentiment analysis to maintain the continuity of the underlying features of these two tasks. The proposed method called Large language model Automatically Labeled and Dansenet for Multimodal (LALDM). The experimental results show that the proposed method improves the performance of existing methods in MABSA tasks. In addition, LALDM has been applied to a cross modal semantic understanding task for online consumer electronics, and experimental results show that it has better performance than the control algorithms.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".